Adversarial Robustness

Adversarial Robustness evaluates the vulnerabilities of machine learning models under various types of adversarial attacks.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 376–400 of 1746 papers

Title	Date	Tasks	Status	Hype
Boosting Adversarial Training via Fisher-Rao Norm-based Regularization	Mar 26, 2024	Adversarial Robustness	CodeCode Available	0
Ensemble Adversarial Defense via Integration of Multiple Dispersed Low Curvature Models	Mar 25, 2024	Adversarial DefenseAdversarial Robustness	—Unverified	0
Towards Adversarial Robustness And Backdoor Mitigation in SSL	Mar 23, 2024	Adversarial RobustnessBackdoor Attack	CodeCode Available	0
Few-Shot Adversarial Prompt Learning on Vision-Language Models	Mar 21, 2024	Adversarial RobustnessAdversarial Text	CodeCode Available	1
DD-RobustBench: An Adversarial Robustness Benchmark for Dataset Distillation	Mar 20, 2024	Adversarial AttackAdversarial Robustness	CodeCode Available	0
Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising	Mar 18, 2024	Adversarial RobustnessDenoising	—Unverified	0
Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization	Mar 18, 2024	Adversarial RobustnessImage Quality Assessment	CodeCode Available	1
Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM	Mar 18, 2024	Adversarial AttackAdversarial Defense	CodeCode Available	0
Understanding Robustness of Visual State Space Models for Image Classification	Mar 16, 2024	Adversarial Robustnessimage-classification	CodeCode Available	0
Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction	Mar 16, 2024	Adversarial RobustnessImage-text Retrieval	—Unverified	0
Benchmarking Adversarial Robustness of Image Shadow Removal with Shadow-adaptive Attacks	Mar 15, 2024	Adversarial AttackAdversarial Robustness	—Unverified	0
Towards Adversarially Robust Dataset Distillation by Curvature Regularization	Mar 15, 2024	Adversarial RobustnessDataset Distillation	CodeCode Available	0
Robust Subgraph Learning by Monitoring Early Training Representations	Mar 14, 2024	Adversarial RobustnessDecision Making	—Unverified	0
Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement	Mar 14, 2024	Adversarial RobustnessMemorization	—Unverified	0
Adversarial Fine-tuning of Compressed Neural Networks for Joint Improvement of Robustness and Efficiency	Mar 14, 2024	Adversarial RobustnessModel Compression	CodeCode Available	0
Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning	Mar 11, 2024	Adversarial RobustnessDeep Learning	—Unverified	0
PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutor	Mar 11, 2024	Adversarial Robustness	CodeCode Available	1
Speech Robust Bench: A Robustness Benchmark For Speech Recognition	Mar 8, 2024	Adversarial RobustnessAutomatic Speech Recognition	CodeCode Available	1
Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolume	Mar 8, 2024	Adversarial RobustnessBenchmarking	—Unverified	0
DF-RAP: A Robust Adversarial Perturbation for Defending against Deepfakes in Real-world Social Network Scenarios	Mar 5, 2024	Adversarial RobustnessFace Swapping	CodeCode Available	1
One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models	Mar 4, 2024	Adversarial AttackAdversarial Robustness	CodeCode Available	2
Enhancing the "Immunity" of Mixture-of-Experts Networks for Adversarial Defense	Feb 29, 2024	Adversarial DefenseAdversarial Robustness	—Unverified	0
Catastrophic Overfitting: A Potential Blessing in Disguise	Feb 28, 2024	Adversarial Robustness	—Unverified	0
Extreme Miscalibration and the Illusion of Adversarial Robustness	Feb 27, 2024	Adversarial AttackAdversarial Robustness	—Unverified	0
Robustness-Congruent Adversarial Training for Secure Machine Learning Model Updates	Feb 27, 2024	Adversarial Robustnessregression	—Unverified	0

Show:10 25 50

← PrevPage 16 of 70Next →

All datasets AdvGLUE CIFAR-10 ImageNet ImageNet-A ImageNet-C Stylized ImageNet CIFAR-100

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	DeBERTa (single model)	Accuracy	0.61	—	Unverified
2	ALBERT (single model)	Accuracy	0.59	—	Unverified
3	T5 (single model)	Accuracy	0.57	—	Unverified
4	SMART_RoBERTa (single model)	Accuracy	0.54	—	Unverified
5	FreeLB (single model)	Accuracy	0.5	—	Unverified
6	RoBERTa (single model)	Accuracy	0.5	—	Unverified
7	InfoBERT (single model)	Accuracy	0.46	—	Unverified
8	ELECTRA (single model)	Accuracy	0.42	—	Unverified
9	BERT (single model)	Accuracy	0.34	—	Unverified
10	SMART_BERT (single model)	Accuracy	0.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Mixed classifier	Accuracy	95.23	—	Unverified
2	Stochastic-LWTA/PGD/WideResNet-34-10	Accuracy	92.26	—	Unverified
3	Stochastic-LWTA/PGD/WideResNet-34-5	Accuracy	91.88	—	Unverified
4	GLOT-DR	Accuracy	84.13	—	Unverified
5	TRADES-ANCRA/ResNet18	Accuracy	81.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ResNet-50 (SGD, Cosine)	Accuracy	77.4	—	Unverified
2	ResNet-50 (SGD, Step)	Accuracy	76.9	—	Unverified
3	DeiT-S (AdamW, Cosine)	Accuracy	76.8	—	Unverified
4	ResNet-50 (AdamW, Cosine)	Accuracy	76.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DeiT-S (AdamW, Cosine)	Accuracy	12.2	—	Unverified
2	ResNet-50 (SGD, Cosine)	Accuracy	3.3	—	Unverified
3	ResNet-50 (SGD, Step)	Accuracy	3.2	—	Unverified
4	ResNet-50 (AdamW, Cosine)	Accuracy	3.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ResNet-50 (AdamW, Cosine)	mean Corruption Error (mCE)	59.3	—	Unverified
2	ResNet-50 (SGD, Step)	mean Corruption Error (mCE)	57.9	—	Unverified
3	ResNet-50 (SGD, Cosine)	mean Corruption Error (mCE)	56.9	—	Unverified
4	DeiT-S (AdamW, Cosine)	mean Corruption Error (mCE)	48	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DeiT-S (AdamW, Cosine)	Accuracy	13	—	Unverified
2	ResNet-50 (SGD, Cosine)	Accuracy	8.4	—	Unverified
3	ResNet-50 (SGD, Step)	Accuracy	8.3	—	Unverified
4	ResNet-50 (AdamW, Cosine)	Accuracy	8.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Mixed Classifier	Clean Accuracy	85.21	—	Unverified
2	ResNet18/MART-ANCRA	Clean Accuracy	60.1	—	Unverified